Conference paper · 2026 · Open access

GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference

Hongjia Wu, Shuai Zhou, 张宏新, Gang Xiong

IEEE International Conference on Automation Science and Engineering (CASE), 3131–3136 · Published 1 August 2026 · DOI 10.1109/case69030.2026.11704481

Open full textCite this paper

In brief

“GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference” is a 2026 conference paper by Hongjia Wu and 3 co-authors, published in IEEE International Conference on Automation Science and Engineering (CASE). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE International Conference on Automation Science and Engineering (CASE).

Citations
0
References
24
Authors
4

Abstract

Urban firefighting resource allocation requires dynamically adjusting equipment ratios to regional risk profiles. This inherently multi-criteria problem involves systematic trade-offs across equipment types and risk dimensions; yet traditional methods' rigid dependence on domain experts limits scalability in dynamic settings. Large language models (LLMs) can substitute for expert judgment, but their logical inconsistencies impede integration with mathematical decision frameworks. This paper proposes GenMCDM, a generative multicriteria decision-making framework using LLMs as knowledge source and Fuzzy AHP as decision backbone, to adaptively generate differentiated resource allocations from urban risk semantics. It accomplishes end-to-end inference from textual semantics to physical provisioning via structural prior extraction, alternative-layer weight injection, multi-agent aggregation with consistency correction, and mapping from risk weights to increments. On a firefighting equipment allocation task, GenMCDM achieves a$\mathbf{1 0 0} \boldsymbol{\%}$consistency pass rate (baseline: 3.5%) and outperforms the end-to-end LLM baseline with a$\mathbf{7 0 \%}$win rate across 20 blind-evaluated scenarios$(\boldsymbol{p} \boldsymbol{<} \mathbf{0. 0 1})$.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wu, H., Zhou, S., 张宏新, & Xiong, G. (2026). GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference. IEEE International Conference on Automation Science and Engineering (CASE), 3131–3136. https://doi.org/10.1109/case69030.2026.11704481

MLA 9

Wu, Hongjia, et al. “GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference.” IEEE International Conference on Automation Science and Engineering (CASE), 2026, pp. 3131–3136. https://doi.org/10.1109/case69030.2026.11704481.

Chicago

Wu, Hongjia, Shuai Zhou, 张宏新, and Gang Xiong. 2026. “GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference.” IEEE International Conference on Automation Science and Engineering (CASE): 3131–3136. https://doi.org/10.1109/case69030.2026.11704481.

Harvard

Wu, H. et al. (2026) ‘GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference’, IEEE International Conference on Automation Science and Engineering (CASE), pp. 3131–3136. doi:10.1109/case69030.2026.11704481.

IEEE

H. Wu, S. Zhou, 张宏新, and G. Xiong, “GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference,” IEEE International Conference on Automation Science and Engineering (CASE), pp. 3131–3136, 2026, doi: 10.1109/case69030.2026.11704481.

BibTeX

@inproceedings{wu2026genmcdm,
  title     = {{GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference}},
  author    = {Wu, Hongjia and Zhou, Shuai and 张宏新 and Xiong, Gang},
  booktitle = {IEEE International Conference on Automation Science and Engineering (CASE)},
  year      = {2026},
  pages     = {3131--3136},
  doi       = {10.1109/case69030.2026.11704481},
  url       = {https://doi.org/10.1109/case69030.2026.11704481}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Decision Sciences › Management Science and Operations Research › Multi-Criteria Decision Making

  • firefighting resource allocation
  • urban firefighting
  • large language models
  • multi-criteria decision making
  • fuzzy analytic hierarchy process

Work with this paper

Most-cited papers in Decision Sciences

All highly cited Decision Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Wu, H., Zhou, S., 张宏新, & Xiong, G. (2026). GenMCDM: Tailoring Firefighting Asset Allocation to Urban Contexts via LLM-Based Inference. IEEE International Conference on Automation Science and Engineering (CASE), 3131–3136. https://doi.org/10.1109/case69030.2026.11704481

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE International Conference on Automation Science and Engineering (CASE): sign in and open the full text from this page.

Who wrote this paper?

Hongjia Wu, Shuai Zhou, 张宏新, Gang Xiong.

What is the DOI of this paper?

10.1109/case69030.2026.11704481, permanently at https://doi.org/10.1109/case69030.2026.11704481. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.